PhilipQuirke commited on
Commit
e52d835
·
verified ·
1 Parent(s): c832bfb

Update model card with revised readme

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -9,6 +9,7 @@ This repository contains a transformer model that can predict both addition and
9
  - **Attention Heads**: 4
10
  - **Training steps**: 85,000
11
  - **Random seed**: 572091
 
12
  **Contents**:
13
  - `model.pth`: The trained transformer model.
14
  - `training_loss.json`: Data gathered during model training (used to plot "loss over training batches").
 
9
  - **Attention Heads**: 4
10
  - **Training steps**: 85,000
11
  - **Random seed**: 572091
12
+
13
  **Contents**:
14
  - `model.pth`: The trained transformer model.
15
  - `training_loss.json`: Data gathered during model training (used to plot "loss over training batches").